Giter Site home page Giter Site logo

mattifrind / detectron-trainings-visualization Goto Github PK

View Code? Open in Web Editor NEW
19.0 2.0 2.0 5.47 MB

Software to visualize detectron training stats

License: GNU Affero General Public License v3.0

Java 99.74% CSS 0.26%
detectron deep-learning caffe2 loss regression accuracy training-stats chart detectron-trainings-visualization training

detectron-trainings-visualization's Introduction

Detectron trainings visualization

With this software you can visualize your Detectron training process. The software reads the accuracy, the loss, the loss_cls and the loss_bbox.

To get started just unpack the vis-tool.zip and start the "train-vis.jar" in the zip-folder "vis-tool.zip".

When you train you network just save the standard out into a file and paste it into the software directory. For example use this command:

python2 tools/train_net.py --cfg path/to/config/file.yaml OUTPUT_DIR path/to/output/directory | tee /home/ubuntu/output/trainingsoutput.txt

You can configure the chart with the form at the start of the tool. Select the higher boundaries as well as the ticks and choose which data you want to show. You can also create a linear regression of the accuracy.

When you run the software you should get a chart like this: example chart

For more information visit my website.

References

detectron-trainings-visualization's People

Contributors

mattifrind avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar

Forkers

hzhang57 daijucug

detectron-trainings-visualization's Issues

Could you kindly add a description on how to use this tool?

Thank you for your tool provided here. I am also interested in using a visualization tool in Detectron which leads me here, but I don't have an idea how to use your tool. Could you kindly add a description on how to use it? Like in README.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.